TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Meta Employees: AI Team Is in "Panic Mode" After DeepSeek R1 Model Release

15 点作者 Babawomba4 个月前

1 comment

Jasondells4 个月前
DeepSeek is a censored product and by that of limited use for anything that might require prompts that are about anything that is somehow &quot;controversial&quot; in the eyes of the CCP. However, the censorship seems to be applied for certain prompts and doesn&#x27;t seem to be integrated into the model itself as the answers given to such prompts are very similar and generic.<p>Has anybody already been able to successfully use prompt jailbreaking or other tricks to overcome this? It would be interesting to see what DeepSeek actually knows instead of what it is responding.<p>Censoring a model via selective training data or post-training is much more difficult.<p>The possible &quot;solutions&quot; applied to this &quot;problem&quot; (in the eyes of the censors) will be of high importance moving forward.<p>Other gov. actors also have an interest in altering models, let&#x27;s not forget.
评论 #42842326 未加载
评论 #42843463 未加载
评论 #42843351 未加载